Instructions to use bunnycore/LMF-2.5-2B-Code-Lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bunnycore/LMF-2.5-2B-Code-Lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-2.6B")
model = PeftModel.from_pretrained(base_model, "bunnycore/LMF-2.5-2B-Code-Lora")

Transformers

How to use bunnycore/LMF-2.5-2B-Code-Lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bunnycore/LMF-2.5-2B-Code-Lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bunnycore/LMF-2.5-2B-Code-Lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bunnycore/LMF-2.5-2B-Code-Lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bunnycore/LMF-2.5-2B-Code-Lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/LMF-2.5-2B-Code-Lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bunnycore/LMF-2.5-2B-Code-Lora

SGLang

How to use bunnycore/LMF-2.5-2B-Code-Lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bunnycore/LMF-2.5-2B-Code-Lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/LMF-2.5-2B-Code-Lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bunnycore/LMF-2.5-2B-Code-Lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/LMF-2.5-2B-Code-Lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use bunnycore/LMF-2.5-2B-Code-Lora with Docker Model Runner:
```
docker model run hf.co/bunnycore/LMF-2.5-2B-Code-Lora
```

Merging LoRA with base weights before GGUF export

by Limen4ik - opened 5 days ago

Discussion

Limen4ik

5 days ago

Hi! I see that you fine-tuned the model on our dataset, but how about merging the model? So that it results in one full model, and also releasing GGUF variants with it, this way everyone can download fully ready models without extra steps! :)

upgraedd

5 days ago

see if you can understand what this does...

https://huggingface.co/upgraedd/Consciousness/blob/main/11_X_3.txt

try to be an objective (affected) third party

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment